No abstract

Synapses Abstractfor computer applications. With an artificial neural network scheme, Josephson devices will be expected to develop a new paradigm for future computer systems. Here we will discuss circuit configurations for a neuron with Josephson devices. We propose a combination of a variable bias source and Josephson devices for a synapse circuit. The bias source signal is steered by the Josephson device input signal and becomes the synapse output signal. These output signals are summed up at the specific resistor or inductor to produce the weighted sum of Josephson devices input signals. According to the error signal, the bias source value is corrected. This corresponds to the learning procedure. Because Josephson devices are threshold logic circuits themselves, they are employed as soma circuits. We also discuss the cell structure of the artificial neural network.

A three-terminal superconducting device composed of a semiconductor-coupled Josephson junction and an oxide-insulated gate is fabricated. A p-type Si single-crystal film having a 100-nm thickness is used for the semiconductor layer. Two superconducting electrodes of the Josephson junction correspond to source and drain electrodes of the three-terminal device. Josephson tunneling current flows between source and drain electrodes, and is controlled by the gate bias voltage.

No abstract

No abstract